Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ghost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imageName
    -0.09
    (New
    -0.07
     Elsa
    -0.07
    cke
    -0.07
     derp
    -0.07
     Luft
    -0.07
    ampie
    -0.07
     delt
    -0.07
    viders
    -0.06
     Refugee
    -0.06
    POSITIVE LOGITS
    ,Y
    0.08
    有时
    0.07
     CAD
    0.07
    ○
    0.07
     unprecedented
    0.07
     incremented
    0.07
    央
    0.07
     DataFrame
    0.06
    先生
    0.06
     указ
    0.06
    Act Density 0.001%

    No Known Activations